Search Results (4)

Indonesia has a variety of ethnic languages, most of which belong to the same language family: the Austronesian languages. Due to the shared language family, words in Indonesian ethnic languages are very similar. However, previous research suggests that these Indonesian ethnic languages are endangered. Thus, to prevent that, we propose the creation of a bilingual dictionary between ethnic languages, using a neural network approach to extract transformation rules, employing character-level embedding and the Bi-LSTM method in a sequence-to-sequence model. The model has an encoder and decoder. The encoder reads the input sequence character by character, generates context, and then extracts a summary of the input. The decoder produces an output sequence wherein each character at each timestep, as well as the subsequent character output, are influenced by the previous character. The first experiment focuses on Indonesian and Minangkabau languages with 10,277 word pairs. To evaluate the model’s performance, five-fold cross-validation was used. The character-level seq2seq method (Bi-LSTM as an encoder and LSTM as a decoder) with an average precision of 83.92% outperformed the SentencePiece byte pair encoding (vocab size of 33) with an average precision of 79.56%. Furthermore, to evaluate the performance of the neural network model in finding the pattern, a rule-based approach was conducted as the baseline. The neural network approach obtained 542 more correct translations compared to the baseline. We implemented the best setting (character-level embedding with Bi-LSTM as the encoder and LSTM as the decoder) for four other Indonesian ethnic languages: Malay, Palembang, Javanese, and Sundanese. These have half the size of input dictionaries. The average precision scores for these languages are 65.08%, 62.52%, 59.69%, and 58.46%, respectively. This shows that the neural network approach can identify transformation patterns of the Indonesian language to closely related languages (such as Malay and Palembang) better than distantly related languages (such as Javanese and Sundanese). Full article

This study investigates traditional culture as one of the factors of the longevity and cross-generation sustainability of Sundanese small industries in Indonesia. The failure rate of small industries in Indonesia is high, and thus, this study is critical. We mapped the relationship between Hofstede’s cultural dimensions, longevity, and business sustainability in ten selected Sundanese small industries surviving up to three generations. Data were obtained from semi-structured interviews and company data. The results revealed that the strength of Sundanese cultural traditions, including high long-term orientation, high collectivism, low power distance, and high indulgences, positively contribute to the longevity of small industries in Indonesia. In addition, the social performance of Sundanese entrepreneurs is mainly based on their religious values and a highly collectivist culture; educational experience also affects their environmental performance. This study highlights the need to understand the traditional culture, which can play an essential role in achieving business longevity but also can present some limitations, especially in terms of economic performance. Therefore, to create a sustainable small industry, efforts are needed to change the mindset of Sundanese entrepreneurs to be more open to an innovative global culture while maintaining local values that positively contribute to business. Full article

This paper presents a comprehensive test of the principal tasks in document image analysis (DIA), starting with binarization, text line segmentation, and isolated character/glyph recognition, and continuing on to word recognition and transliteration for a new and challenging collection of palm leaf manuscripts from Southeast Asia. This research presents and is performed on a complete dataset collection of Southeast Asian palm leaf manuscripts. It contains three different scripts: Khmer script from Cambodia, and Balinese script and Sundanese script from Indonesia. The binarization task is evaluated on many methods up to the latest in some binarization competitions. The seam carving method is evaluated for the text line segmentation task, compared to a recently new text line segmentation method for palm leaf manuscripts. For the isolated character/glyph recognition task, the evaluation is reported from the handcrafted feature extraction method, the neural network with unsupervised learning feature, and the Convolutional Neural Network (CNN) based method. Finally, the Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) based method is used to analyze the word recognition and transliteration task for the palm leaf manuscripts. The results from all experiments provide the latest findings and a quantitative benchmark for palm leaf manuscripts analysis for researchers in the DIA community. Full article

School lunch is not provided in public elementary schools in Indonesia, and students frequently buy and eat snacks at school. We hypothesized that providing a traditional Sundanese meal as school lunch would be beneficial for children in rural West Java. To test this hypothesis, we evaluated the effect of a 1-month school lunch intervention aiming at sustainability and based on children’s nutritional intake, hemoglobin and hematocrit levels, and body mass index (BMI). A lunch (including rice, vegetable dish, animal protein dish, plant protein dish, and fruit) containing one-third of the recommended daily allowance of energy was offered every school day for 1 month, targeting 68 fourth-grade elementary schoolchildren. At baseline, the prevalence of anemia was 33.3%. The prevalence of stunting and underweight were 32.4% and 2.9%, respectively, whereas that of overweight and obesity combined was 17.6%, indicating a double burden of malnutrition among the subjects. During the intervention, intakes of protein (p < 0.05), calcium (p < 0.05), and vitamin C (p < 0.001) significantly increased, while that of fat significantly decreased (p < 0.001). After the intervention, hemoglobin (p < 0.05) and hematocrit (p < 0.05) levels were significantly improved, thereby almost halving the rate of anemia. These changes were significantly larger in the baseline anemic group than the non-anemic group (p < 0.01). BMI significantly increased in the baseline underweight/normal group (p < 0.001) but not in the overweight/obese group. The school lunch intervention significantly improved nutritional intakes and health statuses, implying its potential for reducing anemia and resolving the double burden of malnutrition among rural Indonesian schoolchildren. Full article